In this paper, we present an empirical evaluation of the randomness of the ciphertext blocks generated by the Advanced Encryption Standard (AES) cipher in Counter (CTR) mode and in Cipher Block Chaining (CBC) mode. Vulnerabilities have been found in the AES cipher that may lead to a reduction in the randomness of the generated ciphertext blocks that can result in a practical attack on the cipher. We evaluate the randomness of the AES ciphertext using the standard key length and NIST randomness tests. We evaluate the randomness through a longitudinal analysis on 200 billion ciphertext blocks using logistic regression and a dense neural network. We also trained a dense neural network on thirty billion sequential CBC blocks. Each of these models targeted a single bit location in ciphertext but none resulted in a prediction accuracy greater than 50%. We were unable to find evidence that AES ciphertext is not random, and we conclude that AES remains a safe cipher to use in modern cryptography applications.
Geislinger, Dana; Thigpen, Cory; and Engels, Daniel W.
"Longitudinal Analysis with Modes of Operation for AES,"
SMU Data Science Review: Vol. 2:
2, Article 5.
Available at: https://scholar.smu.edu/datasciencereview/vol2/iss2/5
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License